Abstract: Methods and systems for detection and communication of wireless broadband degradation involve comparing time-series data obtained from wireless sensing with time-series data representing changes in a measure of the quality of service offered by a wireless link. The wireless sensing time-series data is analyzed to detect physical activity in the vicinity of a wireless router, extender, or mesh unit, for instance. If the analysis reveals a correlation between a period of volatility in the time-series data obtained from wireless sensing with a time of a persistent change in the quality of service over a link involving the wireless router, extender or mesh unit, then an alert is transmitted to a provider or user of the wireless network. The alert may indicate that human action may have resulted in the change in quality of service. The user may then take action to reverse the human action if required or desired.

Abstract: Systems and methods for controlling a head-up display are disclosed. A head-up display including a plurality of graphical elements, each graphical element being generated at one of a range of depths on the head-up display is generated on a head-up display device. An indication that one of the graphical elements is currently selected is displayed. A user interface navigation signal to rotate the selection through the graphical elements in order of depth in response to user actuation of a navigation control is received from a user input device and an action associated with the currently selected graphical element in response to user actuation of the user input device is performed.

Abstract: Systems and methods of generating guidance for deliveries and monitoring delivered items are disclosed. A visual anchor is associated with at least a portion of a physical location of a destination for delivering a package. Based on delivery instructions for the package, a visual object corresponding to the visual anchor is created. When a match is detected between the visual anchor and the portion of the physical location as displayed within the field of view of a device, the visual object is overlaid on the portion of the physical location as displayed within the field of view of the device. Based on wireless signal characteristics extracted from a designated drop-off area of the delivery address, a user interacting with the package may be detected. If the user's wireless signal characteristic signature indicates that they are unauthorized to interact with the package, an action is performed addressing the unauthorized interaction.

Abstract: Systems and methods are described for providing media content to occupants of a vehicle. First data associated with a current use state of a vehicle is obtained. The first data is analysed to identify a contextual event regarding the vehicle. In response to identifying the contextual event, second data comprising media content data is requested. A media content item is generated, based on the media content data, relevant to the identified contextual event, and the media content item is provided for consumption by an occupant of the vehicle.

Abstract: Systems and methods are provided for optimizing a user interface display in a video conferencing environment. In some embodiments, the systems and methods receive conference feeds for each of a plurality of participants in a video conference. In some embodiments, the systems determine, based on historical interaction data for one or more participants of the plurality of participants, an interaction score for the one or more participants of the plurality of participants. In some embodiments, the systems generate, based on the determined interaction score, a first arrangement of representations of the conference feeds in a user interface. In some embodiments, the systems provide for presentation in the user interface the first arrangement of the conference feeds.

Abstract: Systems and methods are provided for optimizing reengagement with a content item by leveraging advanced memory-related techniques. At a first time, a user is determined to be disengaged from consuming a content item at a first position within the content item. A reengagement cue is determined by selecting a plurality of portions of the content item, wherein the plurality of portions of the content item are positioned in the content item prior to the first position within the content item. A respective memorability score is determined for each of the plurality of portions. A subset of the plurality of portions is identified based on the respective memorability scores. The reengagement cue is generated based at least part of each of the portions in the subset. At a second time, based at least in part on receiving a request to reengage with the content item, the reengagement cue is presented.

Abstract: Systems and methods for enabling control of various functions of a vehicle based on which occupant made a control input are described. In an example, a method includes determining which occupant of the vehicle is interacting with the vehicle user interface (UI) based on image data or an RF signal coupled to the occupant making the control input, and then responsively executing an action corresponding to the control input only if the occupant making the control input is permitted to do so.

Abstract: Systems and methods for enhancing a live scene to be captured by a camera of a user device based on one or more best matched reference images that include similar subject matter and attributes of the live scene are disclosed. A preview of a live scene is displayed on the user device. Attributes of the live scene are identified. The live scene is segmented separately into a foreground and a background. Vector representations of the attributes of the segmented live scene are calculated and user device parameters are obtained, and both are used to identify reference images that include the attributes of the live scene. The identified reference images are displayed on the user device and a selection is made. The user device parameters are configured based on the selection made to capture the live scene to obtain similar effects of the selected reference image.

Abstract: Systems and methods are disclosed for modifying inferencing of machine learning (ML) models. Based on a first input and session context data, an ML model may generate a first plurality of output tokens. Based on supplemental context data, a first one or more tokens from the first plurality of output tokens may be identified. A second input may be generated based on the identified first one or more tokens, the supplemental context data, or both. The second input may be provided to the ML model. Based on the second input, session context data, supplemental context data, or a combination thereof, the ML model may generate a second plurality of output tokens. In response to the first input and the second input, an output based on the first plurality of tokens, the second plurality of tokens, and supplemental context data may be provided.

Abstract: Systems, vehicles, and methods are disclosed herein for providing transportation options. In relation to a ride request to transport a user from a first location to a second location, and a desired arrival time for the user to arrive at the second location, the system may identify a plurality of estimated transportation durations, each respectively corresponding to a drop-off location at or within a proximity of the second location, and each enabling the user to arrive at the second location by the desired arrival time. The system may select a first estimated transportation duration associated with a first drop-off location, based on an estimated transportation duration to transport the user from the first location to the first drop-off location and an estimated transportation duration for a second mode of transportation to enable the user to arrive at the second location from the first drop-off location.

Abstract: Systems and methods for transmitting supplemental content via an MoQ relay device are described herein. The MoQ relay device establishes a bi-directional connection with each of a publisher, a supplemental content server, and a client device. The MoQ relay receives a media stream via the bi-directional connection with the publisher, the media stream including a plurality of groups made up of objects. The MoQ relay then determines that an initial object of a particular group within the media stream corresponds to an insertion point for supplemental content and sends a request for supplemental content to the supplemental content server via the bi-directional connection. The MoQ relay subsequently receives the supplemental content and transmits the supplemental content to the client device via the bi-directional connection in place of the group corresponding to the insertion point.

Abstract: Systems and methods are described herein for detecting and identifying hazardous material on a roadway and causing a vehicle to perform an action in response. The disclosed methods use one or more sensor devices (e.g., an IR camera) to capture data associated with material located within a surrounding environment of the vehicle. The detected material may be determined to be hazardous by analyzing an image of the material captured by the sensor devices. Based on a determined size and location of the hazardous material, the system may determine that a hazardous material event is imminent (e.g., an interaction between one or more vehicles and the material). The vehicle then performs an action to ameliorate the hazardous material event, such as implementing one or more suggested driving maneuvers to avoid an impact with the hazardous material and/or notifying nearby drivers of information related to the hazardous material event.

Abstract: Systems and methods are provided herein for enabling end-to-end radio slicing between networks of different types. This may be accomplished by an access point receiving data traffic for a session. The data traffic may be received from a first device and may be destined for a second device, where the second device is part of a different licensed network than the first device or the second device is part of an unlicensed network. The access point may determine a performance metrics (e.g., a desired latency, a desired bandwidth, a desired jitter, etc.) associated with the session. The performance metric may be used to select a channel to transmit the data traffic to the second device. The access point may select a first channel of a plurality of channels based, at least in part, on an attribute associated with the first channel and the performance metric associated with the session.

Abstract: Systems and methods are provided for applying an extended reality (XR) effect to a portion of a video comprising a user. A video of a user in an environment is obtained via a camera of a user device. Infrared (IR) light is projected onto the user. IR light reflection data corresponding to the projected light reflected by an object being held by the user is detected. The IR light reflection data is compared to baseline profile data of the user. Based on the comparing, a position of the object is determined to be within a threshold proximity of the user and an XR visual effect is applied to a portion of the video comprising the user.

Abstract: Systems and methods are provided for providing feedback to a user during a virtual tutorial associated with providing an extended reality (XR) visual effect. A video of a user holding an object proximate to their face is obtained via a camera of a user device. A virtual tutorial for performing an action to a region of the user is provided to the user device. A position of the object relative to the user is monitored. While the object is within a threshold proximity of the region, first feedback indicative of correct positioning based on the virtual tutorial is provided to the user. While the object is outside the threshold proximity, second feedback indicative of incorrect positioning based on the virtual tutorial is provided to the user. An XR visual effect is applied to a portion of the video comprising the user based on the position of the object.

Abstract: Methods and systems are disclosed herein for enabling an improved management of a buffer resource of the device during a presentation of a content item, by improving user engagement with content via an adaptable interactive element. A first content item is caused, at a device, to be generated for presentation. Positional data defining a position of an interactive element when presented on the device is determined, wherein the positional data associates the position of the interactive element with a position of a content element presented in the first content item. The interactive element is caused, at the device, to be generated for presentation at a first position based on the positional data.

Abstract: Systems and methods for calendar-based management of QoS parameters of networks are disclosed. Calendar data from a digital calendar is used to identify a scheduled event which utilizes a priority application associated with network priority. A priority level of network service to support performance of the priority application on a device in the network during the scheduled event is determined. A reconfiguration request is transmitted to a networking device of the network. The reconfiguration request causes the networking device to adjust its network QoS parameters according to the priority level of network service and provide a network resource such as bandwidth according to the adjusted network QoS parameters to the priority application during the scheduled event. When the scheduled event has ended, the networking device is instructed to release the network resource.

Abstract: Methods and systems are described herein for the provision of a co-watching companion bot for a media platform. The media platform comprises at least a co-watch bot and a selection of media content. During the play of a media content, a trained multi-modal generative model for the media content is accessed to generate an inferred conversational output. The trained multi-modal generative model is trained on a plurality of indicators, each representing a respective aspect of a respective portion of the media content and uses a context window indicating a portion of the media content provided for playback to generate inferences. The inference is output by way of the co-watch bot upon the media content reaching an initiation point.

Abstract: Methods and systems are described herein for the provision of a co-watching companion bot for a media platform. The media platform comprises at least a co-watch bot and a selection of media content. During the play of a media content, a trained multi-modal generative model for the media content is accessed to generate an inferred conversational output. The trained multi-modal generative model is trained on a plurality of indicators, each representing a respective aspect of a respective portion of the media content and uses a context window indicating a portion of the media content provided for playback to generate inferences. The inference is output by way of the co-watch bot upon the media content reaching an initiation point.

Abstract: Systems and methods are described for enabling wireless communications and various types of engagement between a smart doorbell and a visitor's mobile device based on meeting certain criteria. Systems and methods are also described for establishing peer-to-peer communications between smart doorbells that are joined into a neighborhood watch program for providing alerts and reporting suspicious activity. A geofence around the smart doorbell is set up and a determination is made whether a visitor mobile device is within the generated geofence. If within the geofence, the UI of the visitor mobile device displays the smart doorbell and allows the visitor mobile device to virtually ring the doorbell or communicate with the doorbell if the visitor mobile device satisfies communication criteria of the doorbell. An encrypted peer-to-peer communication is set up, and communication between the doorbell and the visitor mobile device is established.